ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

DeepSeek R1vsMiniMax M3

MiniMax M3 leads 3 of 3 shared benchmarks. MiniMax M3 has the larger context window (1M tokens).

Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.

Shared benchmarks
0 – 3
MiniMax M3 leads
Cheaper per token
list price, input + output
Larger context
MiniMax M3
1M tokens
Provider uptime (30d)
100% · 100%
DeepSeek · MiniMax
DeepSeek R1
DeepSeek · released 2025-01-20
text
Context
128K
Max out
33K
Input /1M
Output /1M
Cached /1M
Scores
8 · 7 core
MiniMax M3
MiniMax · released 2026-06-01
textvision
Context
1M
Max out
Input /1M
$0.3
Output /1M
$1.2
Cached /1M
$0.06
Scores
3 · 3 core
Quality

Benchmark matrix

BenchmarkDeepSeek R1MiniMax M3ΔEdge
Reported by both · 3
GPQA Diamond71.5% 90.9% epoch-19.4 ptMiniMax M3
LMArena Elo1372.6 1433.5 -60.9MiniMax M3
OTIS Mock AIME 2024-2025 (Epoch AI run)53.3% epoch71.1% epoch-17.8 ptMiniMax M3
Only DeepSeek R1 reports · 4
SWE-bench Verified49.2% not reported
MMLU90.8% not reported
MMLU-Pro84% not reported
AIME 202570% matharenanot reported
Only MiniMax M3 reports · 0
MiniMax M3 reports nothing DeepSeek R1 does not.
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is DeepSeek R1 minus MiniMax M3 in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing

Side by side

SpecDeepSeek R1MiniMax M3Edge
Context window128K tokens1M tokensMiniMax M3
Max output33K tokens
Input price / 1M$0.3
Output price / 1M$1.2
Cached input / 1M$0.06
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$1.5
Modalitiestexttext · visionMiniMax M3
Released2025-01-202026-06-01
Cited benchmark scores83
Reliability

Provider status

All providers
More matchups

DeepSeek R1 vs …

More matchups

MiniMax M3 vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run DeepSeek R1 and MiniMax M3 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.